ci: add tests and gh-actions workflows

.github/workflows/ci.yml

@@ -0,0 +1,48 @@
+name: Run Tests
+
+on:
+  - push
+  - pull_request
+
+jobs:
+  test:
+    runs-on: ubuntu-latest
+    strategy:
+      fail-fast: false
+      matrix:
+        python-version:
+          - '3.9'
+          - '3.10'
+          - '3.11'
+          - '3.12'
+          - '3.13'
+
+    steps:
+    - uses: actions/checkout@v4
+    - name: Set up git-annex
+      run: |
+        sudo apt-get update
+        sudo apt-get install -y git-annex
+    - name: Install Python ${{ matrix.python-version }}
+      uses: actions/setup-python@v5
+      with:
+        python-version: ${{ matrix.python-version }}
+    - name: Install Python dependencies
+      run: |
+        python -m pip install --upgrade pip setuptools wheel
+        python -m pip install tox tox-gh-actions
+    - name: Configure Git for DataLad
+      run: |
+        git config --global user.email "junifer-runner@github.com"
+        git config --global user.name "GitHub Runner"
+
+    - name: Test with tox
+      run: |
+        tox
+    - name: Upload coverage to Codecov
+      uses: codecov/codecov-action@v5
+      with:
+        token: ${{ secrets.CODECOV_TOKEN }}
+        fail_ci_if_error: true
+        flags: junifer
+      if: success() && matrix.python-version == 3.12

changelog.d/4.added.md

@@ -0,0 +1 @@
+Add unit tests and CI workflow

codecov.yml

@@ -0,0 +1,14 @@
+codecov:
+  notify: {}
+  require_ci_to_pass: false
+
+comment:                  # this is a top-level key
+  layout: "reach, diff, flags, files"
+  behavior: default
+  require_changes: false  # if true: only post the comment if coverage changes
+  require_base: no        # [yes :: must have a base report to post]
+
+coverage:
+  status:
+    project: off
+    patch: off

junifer_data/_utils.py

@@ -18,7 +18,7 @@
 logger = logging.getLogger(__name__)
 
 
-def check_dataset(  # noqa: C901
+def check_dataset(
     data_dir: Union[str, Path, None] = None,
     tag: Optional[str] = None,
     hexsha: Optional[str] = None,

junifer_data/tests/test_utils.py

@@ -0,0 +1,92 @@
+"""Tests for junifer_data.utils."""
+
+from pathlib import Path
+
+import pytest
+
+from junifer_data import check_dataset
+
+
+def test_check_dataset_main(tmp_path: Path) -> None:
+    """Test check_dataset with main tag.
+
+    Parameters
+    ----------
+    tmp_path : pathlib.Path
+        Pytest fixture that provides a temporary directory.
+
+    """
+    dataset = check_dataset(data_dir=tmp_path)
+    assert dataset.pathobj.name == "main"
+
+    # Check-out again, should update
+    check_dataset(data_dir=tmp_path)
+
+
+def test_check_dataset_tag_errors(tmp_path: Path) -> None:
+    """Test check_dataset hexsha errors.
+
+    Parameters
+    ----------
+    tmp_path : pathlib.Path
+        Pytest fixture that provides a temporary directory.
+
+    """
+    with pytest.raises(RuntimeError, match="Failed to checkout state"):
+        check_dataset(data_dir=tmp_path, tag="wrong")
+
+
+def test_check_dataset_hexsha_errors(tmp_path: Path) -> None:
+    """Test check_dataset hexsha errors.
+
+    Parameters
+    ----------
+    tmp_path : pathlib.Path
+        Pytest fixture that provides a temporary directory.
+
+    """
+    with pytest.raises(ValueError, match="Cannot verify hexsha for main tag."):
+        check_dataset(data_dir=tmp_path, hexsha="wrong")
+
+    # Now clone the dataset without checking
+    check_dataset(data_dir=tmp_path, tag="1")
+
+    with pytest.raises(ValueError, match="Commit verification failed."):
+        check_dataset(data_dir=tmp_path, tag="1", hexsha="wrong")
+
+    # Check with the right hexsha
+    dataset = check_dataset(
+        data_dir=tmp_path,
+        tag="1",
+        hexsha="e9aecf7b5a2fff82de00d265e02afde42a448647",
+    )
+
+    ds_path = tmp_path / "v1"
+
+    with open(ds_path / "test.txt", "w") as f:
+        f.write("test")
+
+    with pytest.raises(RuntimeError, match="dirty junifer-data"):
+        check_dataset(data_dir=tmp_path, tag="1")
+
+    # We will now update the tag
+    dataset.repo.add((ds_path / "test.txt").as_posix())
+    dataset.repo.commit(msg="update")
+
+    with pytest.raises(ValueError, match="Wrong commit checked out."):
+        check_dataset(data_dir=tmp_path, tag="1")
+
+    # Update tag
+    dataset.repo.tag("v1", options=["-d"])
+    dataset.repo.tag("v1")
+
+    # Does not fail
+    check_dataset(data_dir=tmp_path, tag="1")
+
+    # But does not have the right hexsha
+    with pytest.raises(ValueError, match="Commit verification failed."):
+        check_dataset(
+            data_dir=tmp_path,
+            tag="1",
+            hexsha="e9aecf7b5a2fff82de00d265e02afde42a448647",
+        )

pyproject.toml

@@ -111,6 +111,8 @@ ignore = [
     "D107",
     # use specific rule codes when ignoring type issues
     "PGH003",
+    # ignore too complex expressions
+    "C901",
 ]
 
 [tool.ruff.lint.isort]

tox.ini

@@ -3,7 +3,26 @@ requires =
     tox>=4
 env_list =
     ruff,
-    changelog
+    changelog,
+    coverage,
+    py3{9,10,11,12,13}
+
+[gh-actions]
+python =
+    3.9: py39
+    3.10: py310
+    3.11: py311
+    3.12: coverage
+    3.13: py313
+
+[testenv]
+skip_install = false
+passenv =
+    HOME
+deps =
+    pytest
+commands =
+    pytest
 
 [testenv:ruff]
 description = run ruff
@@ -21,3 +40,33 @@ deps =
     towncrier
 commands =
     towncrier build --draft
+
+[testenv:coverage]
+skip_install = false
+deps =
+    pytest-cov
+commands =
+    pytest --cov={envsitepackagesdir}/junifer_data --cov-report=xml --cov-report=term {envsitepackagesdir}/junifer_data
+
+[coverage:paths]
+source =
+    junifer_data
+    */site-packages/junifer_data
+
+[coverage:run]
+branch = true
+omit =
+    */setup.py
+    */_version.py
+    */tests/*
+parallel = false
+
+[coverage:report]
+exclude_lines =
+    # Have to re-enable the standard pragma
+    pragma: no cover
+    # Type checking if statements should not be considered
+    if TYPE_CHECKING:
+    # Don't complain if non-runnable code isn't run:
+    if __name__ == .__main__.:
+precision = 2